Method and computing system for performing container detection and object detection

Abstract

A system and method for performing object detection are presented. The system receives spatial structure information associated with an object which is or has been in a camera field of view of a spatial structure sensing camera. The spatial structure information is generated by the spatial structure sensing camera, and includes depth information for an environment in the camera field of view. The system determines a container pose based on the spatial structure information, wherein the container pose is for describing at least one of an orientation for the container or a depth value for at least a portion of the container. The system further determines an object pose based on the container pose, wherein the object pose is for describing at least one of an orientation for the object or a depth value for at least a portion of the object.

1 . A computing system comprising:
 a communication interface configured to communicate with a robot having a robot arm that has a spatial structure sensing camera disposed on the robot arm, wherein the spatial structure sensing camera has a camera field of view; and   at least one processing circuit configured to perform the following:
 receiving spatial structure information generated by the spatial structure sensing camera, the spatial structure information including depth information for an environment in the camera field of view, a container, and an object within the container; 
 determining a rim pose of a rim of the container based on the spatial structure information, wherein the rim pose is for describing at least one of an orientation for the rim of the container and/or a depth value for at least a portion of the rim of the container; 
 determining an object pose based on the rim pose, wherein the object pose is for describing at least one of an orientation for the object and/or a depth value for at least a portion of the object; 
 generating a movement command for causing robot interaction with the object, wherein the movement command is generated based on the object pose. 
   
     
     
         2 . The computing system of  claim 1 , wherein a reference plane positioned in the rim pose and intersecting the rim pose does not substantially intersect a major surface of the container. 
     
     
         3 . The computing system of  claim 1 , wherein:
 the container further comprises a first side wall, a top surface of which partially defines the rim of the container; and   the container further comprises a second side wall positioned opposite to and facing the first side wall, a top surface of the second side wall partially defining the rim of the container.   
     
     
         4 . The computing system of  claim 3 , wherein, when viewed in a direction along the rim of the container, neither a top surface nor a bottom surface of the container is positioned directly between the top surface of the first side wall and the top surface of the second side wall. 
     
     
         5 . The computing system of  claim 1 , wherein the rim is a raised edge of the container. 
     
     
         6 . The computing system of  claim 1 , wherein:
 the rim includes an outer edge facing a direction outward of the container, and   the rim includes an inner edge facing a direction inward of the container.   
     
     
         7 . The computing system of  claim 1 , wherein the depth information indicates that an upper edge of the rim is higher than an inner side of the container. 
     
     
         8 . The computing system of  claim 1 , wherein the depth value for at least the portion of the object within the container is a defined distance downward from the rim pose. 
     
     
         9 . The computing system of  claim 1 , wherein the at least one processing circuit is further configured to perform:
 determining a container bottom surface based on the rim pose of the container and based on a defined or identified distance downward of the rim pose; and   determining the object pose based on the container bottom surface and a predefined height of the object.   
     
     
         10 . The computing system of  claim 9 , wherein the predefined height of the object is based on an object identifier disposed on the object. 
     
     
         11 . The computing system of  claim 10 , wherein the object identifier is a one-dimensional or two-dimensional computer readable code. 
     
     
         12 . The computing system of  claim 1 , wherein the at least one processing circuit is further configured to perform:
 determining a location of an object identifier disposed on the object; and   utilizing a location of the object identifier for determining the pose of the object.   
     
     
         13 . The computing system of  claim 12 , wherein the object identifier indicates and/or represents dimensions of the object. 
     
     
         14 . A method for object detection, comprising:
 receiving spatial structure information that includes depth information for an environment in which an object is within a container having a rim;   determining a rim pose of a rim of the container based on the spatial structure information, wherein the rim pose is for describing at least one of an orientation for the rim of the container and/or a depth value for at least a portion of the rim of the container;   determining an object pose based on the rim pose, wherein the object pose is for describing at least one of an orientation for the object and/or a depth value for at least a portion of the object; and   generating a movement command for causing robot interaction with the object, wherein the movement command is generated based on the object pose.   
     
     
         15 . The method for object detection of  claim 14 , wherein a reference plane positioned in the rim pose and intersecting the rim pose does not substantially intersect a major surface of the container. 
     
     
         16 . The method for object detection of  claim 14 , further comprising the steps of:
 determining a container bottom surface based on the rim pose of the container and based on a defined or identified distance downward of the rim pose; and   determining the object pose based on the container bottom surface and a predefined height of the object.   
     
     
         17 . The method for object detection of  claim 16 , wherein the predefined height of the object is based on an object identifier disposed on the object. 
     
     
         18 . A non-transitory computer-readable medium having instructions that, when executed by at least one processing circuit of a computing system, causes the at least one processing circuit to:
 receive spatial structure information that includes depth information for an environment in which an object is within a container having a rim;   determine a rim pose of a rim of the container based on the spatial structure information, wherein the rim pose is for describing at least one of an orientation for the rim of the container and/or a depth value for at least a portion of the rim of the container;   determine an object pose based on the rim pose, wherein the object pose is for describing at least one of an orientation for the object and/or a depth value for at least a portion of the object; and   generate a movement command to cause robot interaction with the object, wherein the movement command is generated based on the object pose.   
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein a reference plane positioned in the rim pose and intersecting the rim pose does not substantially intersect a major surface of the container. 
     
     
         20 . The non-transitory computer-readable medium of  claim 18 , wherein the instructions further cause the at least one processing circuit to:
 determine a container bottom surface based on the rim pose of the container and based on a defined or identified distance downward of the rim pose; and   determine the object pose based on the container bottom surface and a predefined height of the object.